chronology

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). The skill explicitly ingests and parses external, user-provided and declared document sources (see "Step 1: Identify document sources" and "Step 2: Pull + read" — e.g., Google Drive, SharePoint, Gmail, eDiscovery connectors, user uploads, and optional web search), and it uses that content to extract events and drive tagging/next actions, so untrusted third‑party content can materially influence the agent's behavior.